Sharing our Experience Upgrading OpenNMT to TensorFlow 2.0
https://blog.tensorflow.org/2019/11/our-experience-upgrading-OpenNMT-to-TensorFlow.html
code: https://github.com/OpenNMT/OpenNMT-tf
OpenNMT: https://opennmt.net/
https://blog.tensorflow.org/2019/11/our-experience-upgrading-OpenNMT-to-TensorFlow.html
code: https://github.com/OpenNMT/OpenNMT-tf
OpenNMT: https://opennmt.net/
blog.tensorflow.org
Sharing our Experience Upgrading OpenNMT to TensorFlow 2.0
OpenNMT-tf is a neural machine translation toolkit for TensorFlow released in 2017. At that time, the project used many features and capabilities offered by TensorFlow: training and evaluation with tf.estimator, variable scopes, graph collections, tf.contrib…
How to Connect Model Input Data With Predictions for Machine Learning
https://machinelearningmastery.com/how-to-connect-model-input-data-with-predictions-for-machine-learning/
https://machinelearningmastery.com/how-to-connect-model-input-data-with-predictions-for-machine-learning/
MachineLearningMastery.com
How to Connect Model Input Data With Predictions for Machine Learning - MachineLearningMastery.com
Fitting a model to a training dataset is so easy today with libraries like scikit-learn.
A model can be fit and evaluated on a dataset in just a few lines of code. It is so easy that it has become a problem.
The same few lines of code are repeated again…
A model can be fit and evaluated on a dataset in just a few lines of code. It is so easy that it has become a problem.
The same few lines of code are repeated again…
Stacked Capsule Autoencoders
https://github.com/google-research/google-research/tree/master/stacked_capsule_autoencoders
paper : https://arxiv.org/abs/1906.06818
https://akosiorek.github.io/ml/2019/06/23/stacked_capsule_autoencoders.html
https://github.com/google-research/google-research/tree/master/stacked_capsule_autoencoders
paper : https://arxiv.org/abs/1906.06818
https://akosiorek.github.io/ml/2019/06/23/stacked_capsule_autoencoders.html
GitHub
google-research/stacked_capsule_autoencoders at master · google-research/google-research
Google Research. Contribute to google-research/google-research development by creating an account on GitHub.
What Does Stochastic Mean in Machine Learning?
https://machinelearningmastery.com/stochastic-in-machine-learning/
https://machinelearningmastery.com/stochastic-in-machine-learning/
DeepFovea: Using deep learning for foveated reconstruction in AR/VR
https://ai.facebook.com/blog/deepfovea-using-deep-learning-for-foveated-reconstruction-in-ar-vr/
code: https://github.com/facebookresearch/DeepFovea
full paper: https://research.fb.com/publications/deepfovea-neural-reconstruction-for-foveated-rendering-and-video-compression-using-learned-statistics-of-natural-videos/
@ai_machinelearning_big_data
https://ai.facebook.com/blog/deepfovea-using-deep-learning-for-foveated-reconstruction-in-ar-vr/
code: https://github.com/facebookresearch/DeepFovea
full paper: https://research.fb.com/publications/deepfovea-neural-reconstruction-for-foveated-rendering-and-video-compression-using-learned-statistics-of-natural-videos/
@ai_machinelearning_big_data
Facebook
DeepFovea: Using deep learning for foveated reconstruction in AR/VR
We are making available the DeepFovea network architecture, a new state of the art in foveated rendering for augmented and virtual reality using an AI-powered system.
RecSim: A Configurable Simulation Platform for Recommender Systems
https://ai.googleblog.com/2019/11/recsim-configurable-simulation-platform.html
article: https://arxiv.org/abs/1909.04847
github: https://github.com/google-research/recsim
https://ai.googleblog.com/2019/11/recsim-configurable-simulation-platform.html
article: https://arxiv.org/abs/1909.04847
github: https://github.com/google-research/recsim
Googleblog
RecSim: A Configurable Simulation Platform for Recommender Systems
Introducing Hypothesis GU Funcs, an Open Source Python Package for Unit Testing
https://eng.uber.com/hypothesis-gu-funcs-unit-testing/
Hypothesis General Universal Function Documentation
https://hypothesis-gufunc.readthedocs.io/en/latest/
https://eng.uber.com/hypothesis-gu-funcs-unit-testing/
Hypothesis General Universal Function Documentation
https://hypothesis-gufunc.readthedocs.io/en/latest/
Uber Blog
Introducing Hypothesis GU Funcs, an Open Source Python Package for Unit Testing | Uber Blog
Uber introduces Hypothesis GU Func, a new extension to Hypothesis, as an open source Python package for unit testing.
3 Ways to Encode Categorical Variables for Deep Learning
https://machinelearningmastery.com/how-to-prepare-categorical-data-for-deep-learning-in-python/
https://machinelearningmastery.com/how-to-prepare-categorical-data-for-deep-learning-in-python/
MachineLearningMastery.com
3 Ways to Encode Categorical Variables for Deep Learning - MachineLearningMastery.com
Machine learning and deep learning models, like those in Keras, require all input and output variables to be numeric. This means that if your data contains categorical data, you must encode it to numbers before you can fit and evaluate a model. The two most…
This media is not supported in your browser
VIEW IN TELEGRAM
Handtrack.js: tracking hand interactions in the browser using Tensorflow.js and 3 lines of code
https://blog.tensorflow.org/2019/11/handtrackjs-tracking-hand-interactions.html
github: https://github.com/victordibia/handtrack.js/
dataset: https://vision.soic.indiana.edu/projects/egohands/
https://blog.tensorflow.org/2019/11/handtrackjs-tracking-hand-interactions.html
github: https://github.com/victordibia/handtrack.js/
dataset: https://vision.soic.indiana.edu/projects/egohands/
Continual Unsupervised Representation Learning
Paper: https://arxiv.org/abs/1910.14481
Code: https://github.com/deepmind/deepmind-research/tree/master/curl
Paper: https://arxiv.org/abs/1910.14481
Code: https://github.com/deepmind/deepmind-research/tree/master/curl
🔥 Fire and smoke detection with Keras and Deep Learning
https://www.pyimagesearch.com/2019/11/18/fire-and-smoke-detection-with-keras-and-deep-learning/
https://www.pyimagesearch.com/2019/11/18/fire-and-smoke-detection-with-keras-and-deep-learning/
PyImageSearch
Fire and smoke detection with Keras and Deep Learning - PyImageSearch
In this tutorial, you will learn how to detect fire and smoke using Computer Vision, OpenCV, and the Keras Deep Learning library.
Understanding the generalization of ‘lottery tickets’ in neural networks
https://ai.facebook.com/blog/understanding-the-generalization-of-lottery-tickets-in-neural-networks/
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
https://arxiv.org/pdf/1906.02773.pdf
https://arxiv.org/pdf/1906.02768.pdf
https://ai.facebook.com/blog/understanding-the-generalization-of-lottery-tickets-in-neural-networks/
One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers
https://arxiv.org/pdf/1906.02773.pdf
https://arxiv.org/pdf/1906.02768.pdf
Facebook
Understanding the generalization of ‘lottery tickets’ in neural networks
The lottery ticket hypothesis suggests that by training DNNs from “lucky” initializations, we can train networks which are 10-100x smaller with minimal performance losses. In new work, we extend our understanding of this phenomenon in several ways.
Identifying Exoplanets with Neural Networks
https://blog.tensorflow.org/2019/11/identifying-exoplanets-with-neural.html
code: https://github.com/aedattilo/models_K2/tree/master/research/astronet
paper: https://arxiv.org/pdf/1903.10507.pdf
https://blog.tensorflow.org/2019/11/identifying-exoplanets-with-neural.html
code: https://github.com/aedattilo/models_K2/tree/master/research/astronet
paper: https://arxiv.org/pdf/1903.10507.pdf
blog.tensorflow.org
Identifying Exoplanets with Neural Networks
What is an exoplanet? How do we find them? Most importantly, why do we want to find them? Exoplanets are planets outside of our Solar System - they orbit any star other than our Sun.
We can find these exoplanets via a few methods: radial velocity, transits…
We can find these exoplanets via a few methods: radial velocity, transits…
Introducing LIGHT: A multiplayer text adventure game for dialogue research
https://ai.facebook.com/blog/introducing-light-a-multiplayer-text-adventure-game-for-dialogue-research/
Learning in Interactive Games with Humans and Text
https://parl.ai/projects/light/
ParlAI Quick-start
https://parl.ai.s3-website.us-east-2.amazonaws.com/docs/tutorial_quick.html
https://ai.facebook.com/blog/introducing-light-a-multiplayer-text-adventure-game-for-dialogue-research/
Learning in Interactive Games with Humans and Text
https://parl.ai/projects/light/
ParlAI Quick-start
https://parl.ai.s3-website.us-east-2.amazonaws.com/docs/tutorial_quick.html
Facebook
Introducing LIGHT: A multiplayer text adventure game for dialogue research
Learn more about LIGHT, a new large-scale fantasy text adventure game that enable researchers to study language and actions jointly in a game world.
How to Use an Empirical Distribution Function in Python
https://machinelearningmastery.com/empirical-distribution-function-in-python/
https://machinelearningmastery.com/empirical-distribution-function-in-python/
MachineLearningMastery.com
How to Use an Empirical Distribution Function in Python - MachineLearningMastery.com
An empirical distribution function provides a way to model and sample cumulative probabilities for a data sample that does not fit a standard probability distribution.
As such, it is sometimes called the empirical cumulative distribution function, or ECDF…
As such, it is sometimes called the empirical cumulative distribution function, or ECDF…
Optimizing agent behavior over long time scales by transporting value
https://github.com/deepmind/deepmind-research/tree/master/tvt
https://github.com/deepmind/tvt
article: https://arxiv.org/abs/1810.06721
https://github.com/deepmind/deepmind-research/tree/master/tvt
https://github.com/deepmind/tvt
article: https://arxiv.org/abs/1810.06721
GitHub
deepmind-research/tvt at master · deepmind/deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications - deepmind/deepmind-research
High-Throughput, Contact-Free Detection of Atrial Fibrillation From Video With Deep Learning
https://jamanetwork.com/journals/jamacardiology/fullarticle/2756246
https://jamanetwork.com/journals/jamacardiology/fullarticle/2756246
Jamanetwork
High-Throughput, Contact-Free Detection of Atrial Fibrillation From Video With Deep Learning
This study uses video and a pretrained deep convolutional neural network to analyze facial photoplethysmographic signals in detection of atrial fibrillation.
Linear Algebra Vectors.pdf
7.5 MB
Introduction to Applied Linear Algebra – Vectors, Matrices, and Least Squares
https://web.stanford.edu/~boyd/vmls/
@ai_machinelearning_big_data
https://web.stanford.edu/~boyd/vmls/
@ai_machinelearning_big_data
A Gentle Introduction to Model Selection for Machine Learning
https://machinelearningmastery.com/a-gentle-introduction-to-model-selection-for-machine-learning/
https://machinelearningmastery.com/a-gentle-introduction-to-model-selection-for-machine-learning/
MachineLearningMastery.com
A Gentle Introduction to Model Selection for Machine Learning - MachineLearningMastery.com
Given easy-to-use machine learning libraries like scikit-learn and Keras, it is straightforward to fit many different machine learning models on a given predictive modeling dataset. The challenge of applied machine learning, therefore, becomes how to choose…
nbdev: use Jupyter Notebooks for everything
https://www.fast.ai//2019/12/02/nbdev/
github: https://github.com/fastai/nbdev/
https://www.fast.ai//2019/12/02/nbdev/
github: https://github.com/fastai/nbdev/